Transformer core loosening detection method based on acoustic images and platform

Abstract

The invention relates to a transformer core loosening detection method based on acoustic images and a platform. The transformer core loosening detection method comprises the following steps: (1) converting the acoustic images of a transformer core into grey-scale maps; (2) extracting textural features of the acoustic images, and generating a gray level co-occurrence matrix; (3) calculating the characteristic values of the textural features of the selected characterization acoustic images, and calculating the average value and standard deviation of the characteristic values; and (4) comparing the sizes of each characteristic value and corresponding reference values, and according to comparative results, obtaining a compression state of the core. Compared with the prior art, the transformercore loosening detection method has the advantages of high accuracy degree, high antijamming capability, good application prospect and the like.

Description

technical field [0001] The invention relates to a method for monitoring equipment faults in electrical engineering, in particular to a method and platform for detecting loose iron cores of transformers based on acoustic images. Background technique [0002] As the key equipment in the process of power generation, transmission, distribution, and power conversion in the power industry, power transformers are crucial for their safe, stable, and reliable operation. Among them, the iron core plays a vital role in the electromagnetic performance and mechanical strength of the transformer, and the faults caused by iron core problems account for a large proportion of the total faults of the transformer. According to the statistics of the National Energy Administration, in 2017, the main component that caused the outage of main transformers of 220kV and above in my country was the iron core attachment, and its unplanned outage time accounted for as much as 43% of the total time, whic...

AI Technical Summary

Problems solved by technology

[0005] The conventional acoustic method to detect the loose defect of the transformer iron core is generally to collect the acoustic signal radiated by the vibration of the iron core, analyze the signal in the time domain or frequency domain, and obtain the amplitude in the time domain, or the spectrum distribution and various characteristics in the frequency domain There is also a method of using the energy distribution of the characteristic frequency band to change the amplitude at the frequency point, but the above methods are actually based on the continuous time domain data of the acoustic signal. For measurement, the acoustic signal is easily disturbed by the outside world, and the extracted The characteristic parameters of the application are highly uncertain, and the information of a single point is also very limited

At present, the method of acoustic imaging has been gradually applied to the detection of loose defects in power equipment, but there are still many deficiencies in the extraction of acoustic image features, how to correspond to loose defects, and diagnostic criteria.

Images